检索结果-内蒙古大学图书馆

Privacy-Preserving Information Fusion Technique for Device to Server-Enabled Communication in the Internet of Things:A Hybrid Approach

引用

computers, Materials & Continua 2024年第7期80卷 1305-1323页

作者： Amal Al-Rasheed Rahim Khan Tahani Alsaed Mahwish Kundi Mohamad Hanif Md.Saad Mahidur R.Sarker Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science AbdulWali Khan University MardanMardan23200Pakistan Faculty of Computing and Informatics University Malaysia SabahKota KinabaluSabah88400Malaysia Applied College Taibah UniversityMadinah41477Saudi Arabia Maynooth International Engineering College Maynooth UniversityCo KildareW23 X021Irland Department of Mechanical Engineering Faculty of Engineering and Built EnvironmentUniversiti Kebangsaan MalaysiaBangiSelangor43600Malaysia Institute of Visual Informatics Universiti Kebangsaan MalaysiaBangiSelangor43600Malaysia University of Design Innovation and Technology(UDIT)Av.Alfonso XIII97Madrid28016Spain

Due to the overwhelming characteristics of the Internet of Things(IoT)and its adoption in approximately every aspect of our lives,the concept of individual devices’privacy has gained prominent attention from both customers,i.e.,people,and industries as wearable devices collect sensitive information about patients(both admitted and outdoor)in smart healthcare *** addition to privacy,outliers or noise are among the crucial issues,which are directly correlated with IoT infrastructures,as most member devices are resource-limited and could generate or transmit false data that is required to be refined before processing,i.e.,***,the development of privacy-preserving information fusion techniques is highly encouraged,especially those designed for smart IoT-enabled *** this paper,we are going to present an effective hybrid approach that can refine raw data values captured by the respectivemember device before transmission while preserving its privacy through the utilization of the differential privacy technique in IoT *** window,i.e.,δi based dynamic programming methodology,is implemented at the device level to ensure precise and accurate detection of outliers or noisy data,and refine it prior to activation of the respective transmission ***,an appropriate privacy budget has been selected,which is enough to ensure the privacy of every individualmodule,i.e.,a wearable device such as a smartwatch attached to the patient’s *** contrast,the end module,i.e.,the server in this case,can extract important information with approximately the maximum level of ***,refined data has been processed by adding an appropriate nose through the Laplace mechanism to make it useless or meaningless for the adversary modules in the *** proposed hybrid approach is trusted from both the device’s privacy and the integrity of the transmitted information *** and analytical results ha

关键词： Internet of things information fusion differential privacy dynamic programming Laplace function

来源：评论

学校读者我要写书评

暂无评论

Action Localization and Recognition through Unsupervised I3D and TSN 3

Action Localization and Recognition through Unsupervised I3D...

引用

3rd International Conference on Computing and Information Technology, ICCIT 2023

作者： Umran, Munzir Muchtar, Kahlil Abidin, Taufik Fuadi Arnia, Fitri Universitas Syiah Kuala Dept. of Electrical and Computer Engineering Banda Aceh Indonesia Dept. of Electrical and Computer Engineering Banda Aceh Indonesia Universitas Syiah Kuala Faculty of Mathematics and Natural Sciences Department of Informatics Banda Aceh Indonesia

ISBN: (纸本)9798350321487

Since CCTV technology was widely introduced as a video surveillance system, it has become very popular due to increased security concerns. However, detecting suspicious behavior is still done manually by humans, which is inefficient in terms of accuracy and manpower (prone to distraction and fatigue). Many studies use the entire frame of a video to recognize human action, whereas in this study first localize the area of object movement using the unsupervised inflated 3D (I3D) network which produces several frames that have been determined as the region of interest (ROI) from the total frames in the video. Then the collection of ROI frames is generated into a video which will then be classified to recognize human action through the Temporal Segment Networks (TSN). For efficiency purposes, the proposed pipeline can be run separately in the edge (for localization), and cloud environment (for recognition), respectively. The results show that there are 54 classes of ROI video data sets that have an average human action recognition prediction similarity rate above 84.6% which is the average of the prediction similarity rate of the entire ROI video data. In terms of prediction accuracy, 37 classes of data (36.63%) are better than the original class, including 25 classes of data (24.75%) above the threshold, and the processing speed of classification with ROI video data is on average 5 times faster than full-frame video data. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Estimating the AGV load and a battery lifetime based on the current measurement and random forest application

Estimating the AGV load and a battery lifetime based on the ...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Hanzel, Krzysztof Grzechca, Damian Ziebinski, Adam Chruszczyk, Lukas Janus, Artur Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Telecommunications and Teleinformatics Gliwice Poland Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Electronics Electrical Engineering and Microelectronics Gliwice Poland Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Distributed Systems and Informatics Devices Gliwice Poland Silesian University of Technology Student of Electrical EngineeringFaculty of Electrical Engineering Gliwice Poland

ISBN: (纸本)9798350324457

The paper describes the energy consumption from the battery based on the current measurements for various cases, i.e., speed (PWL adjustment) and loads. The main purpose of the research is to have additional and reliable information about power consumption and battery life estimation for autonomous guided vehicles (AGV). The authors propose a two-step algorithm. In the first step, a linear classifier was proposed. Then, the KNN classifier was tested;however, it did not give satisfactory results, so it was finally decided to use the random forest to estimate the load and PWL. The time domain current measurement is evaluated, and the beforementioned algorithms process the selected statistical measures. It has been proven that a two-step algorithm allows for achieving high accuracy. Based on the current observation, the paper is a good starting point for further investigation of the AGV because it is usually implemented in the AGV - so it does not require additional hardware. Moreover, it can lead to better energy management and increase battery lifetime. © 2023 IEEE.

关键词： AGV load estimation machine learning Prediction of energy consumption random forest

来源：评论

学校读者我要写书评

暂无评论

Efficient Cloud Resource Scheduling with an Optimized Throttled Load Balancing Approach

引用

computers, Materials & Continua 2023年第11期77卷 2179-2188页

作者： V.Dhilip Kumar J.Praveenchandar Muhammad Arif Adrian Brezulianu Oana Geman Atif Ikram Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyChennai600062India Department of Computer Science and Engineering Karunya Institute of Technology and SciencesCoimbatoreTamil Nadu641114India Department of Computer Science Superior UniversityLahorePakistan Faculty of Electronics Telecommunications and Information Technology Gheorghe Asachi Technical University of IasiIa¸si700050Romania Department of Health and Human Development Stefan cel Mare University of SuceavaSuceava720229Romania Faculty of Ocean Engineering Technology and Informatics University Malaysia TerengganuKuala NerusMalaysia

Cloud Technology is a new platform that offers on-demand computing Peripheral such as storage,processing power,and other computer system *** is also referred to as a system that will let the consumers utilize computational resources like databases,servers,storage,and intelligence over the *** a cloud network,load balancing is the process of dividing network traffic among a cluster of available servers to increase *** is also known as a server pool or server *** a single node is overwhelmed,balancing the workload is needed to manage unpredictable *** load balancer sends the load to another free node in this *** focus on the Balancing of workflows with the proposed approach,and we present a novel method to balance the load that manages the dynamic scheduling *** of the preexisting load balancing techniques is considered,however it is somewhat modified to fit the scenario at *** on the experimentation’s findings,it is concluded that this suggested approach improves load balancing consistency,response time,and throughput by 6%.

关键词： Load balancing throttled algorithm efficient resource allocation

来源：评论

学校读者我要写书评

暂无评论

UNet Based onMulti-Object Segmentation and Convolution Neural Network for Object Recognition

引用

computers, Materials & Continua 2024年第7期80卷 1563-1580页

作者： Nouf Abdullah Almujally Bisma Riaz Chughtai Naif Al Mudawi Abdulwahab Alazeb Asaad Algarni Hamdan A.Alzahrani Jeongmin Park Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Information Technology Department College of Computing and InformaticsSaudi Electronic UniversityRiyadh13316Saudi Arabia Department of Computer Engineering Korea Polytechnic UniversitySiheung-siGyeonggi-do237Republic of Korea

The recent advancements in vision technology have had a significant impact on our ability to identify multiple objects and understand complex *** technologies,such as augmented reality-driven scene integration,robotic navigation,autonomous driving,and guided tour systems,heavily rely on this type of scene *** paper presents a novel segmentation approach based on the UNet network model,aimed at recognizing multiple objects within an *** methodology begins with the acquisition and preprocessing of the image,followed by segmentation using the fine-tuned UNet ***,we use an annotation tool to accurately label the segmented *** labeling,significant features are extracted from these segmented objects,encompassing KAZE(Accelerated Segmentation and Extraction)features,energy-based edge detection,frequency-based,and blob *** the classification stage,a convolution neural network(CNN)is *** comprehensive methodology demonstrates a robust framework for achieving accurate and efficient recognition of multiple objects in *** experimental results,which include complex object datasets like MSRC-v2 and PASCAL-VOC12,have been *** analyzing the experimental results,it was found that the PASCAL-VOC12 dataset achieved an accuracy rate of 95%,while the MSRC-v2 dataset achieved an accuracy of 89%.The evaluation performed on these diverse datasets highlights a notably impressive level of performance.

关键词： UNet segmentation blob fourier transform convolution neural network

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity of Sensors on Smart Vehicles: Review of Threats and Solutions 6

Cybersecurity of Sensors on Smart Vehicles: Review of Threat...

引用

6th International Conference on computer and informatics engineering, IC2IE 2023

作者： Putro, Prasetyo Adi Wibowo Amelia, Fetty Pidanic, Jan Suhartanto, Heru Rahardjo, Imam Arif Imandeka, Ejo Universitas Indonesia Faculty of Computer Science Depok Indonesia Cryptographic Hardware Engineering Politeknik Siber Dan Sandi Negara Bogor Indonesia University of Pardubice Faculty of Electrical Engineering and Informatics Pardubice Czech Republic Universitas Negeri Jakarta Department of Electrical Engineering Jakarta Indonesia

ISBN: (纸本)9798350345162

The use of sensors in smart vehicles brings benefits and vulnerabilities. Different kinds of sensors in smart vehicles are vulnerable to cyber-attack. Until now, the investigation of challenges and solutions for in-vehicle cybersecurity hasn't discussed various sensor objects and their correlation. In this study, we studied the cyber security problems of sensors in smart vehicles and how to overcome them. The research was designed as Systematic Literature Review (SLR) using the Kitchenham methodology with modification in the filtering phase using the artificial intelligence application, Elicit, to identify the problems, conclusions, and methodology description. Seventeen publications from 2016 until 2023 were gained from five databases. As a result, we find that the most discussed object related to cybersecurity sensors on smart vehicles are Electronic Control Units. Spoofing and jamming is still the most addressed threat, and machine learning is the most utilized solution to be implemented in detection systems. Advanced detection systems are incorporating updated attack models. We also suggest using updated attack models and machine learning algorithms to ensure the safety and security of smart vehicle technology. All identified sensor technology correlated using mind maps under the Intelligent Transport System theory. © 2023 IEEE.

关键词： cybersecurity Kitchenham sensor SLR smart vehicles solution threat

来源：评论

学校读者我要写书评

暂无评论

WildGaussians: 3D Gaussian Splatting in the Wild 38

WildGaussians: 3D Gaussian Splatting in the Wild

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Kulhanek, Jonas Peng, Songyou Kukelova, Zuzana Pollefeys, Marc Sattler, Torsten Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Czech Republic Faculty of Electrical Engineering Czech Technical University in Prague Czech Republic Department of Computer Science ETH Zurich Switzerland Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague Czech Republic

While the field of 3D scene reconstruction is dominated by NeRFs due to their photorealistic quality, 3D Gaussian Splatting (3DGS) has recently emerged, offering similar quality with real-time rendering speeds. However, both methods primarily excel with well-controlled 3D scenes, while in-the-wild data - characterized by occlusions, dynamic objects, and varying illumination - remains challenging. NeRFs can adapt to such conditions easily through per-image embedding vectors, but 3DGS struggles due to its explicit representation and lack of shared parameters. To address this, we introduce WildGaussians, a novel approach to handle occlusions and appearance changes with 3DGS. By leveraging robust DINO features and integrating an appearance modeling module within 3DGS, our method achieves state-of-the-art results. We demonstrate that WildGaussians matches the real-time rendering speed of 3DGS while surpassing both 3DGS and NeRF baselines in handling in-the-wild data, all within a simple architectural framework. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Maternal Health Risk Classification - A Comparison between Algorithm Decision Tree and k-Nearest Neighbor (kNN)

Maternal Health Risk Classification - A Comparison between A...

引用

2023 International Conference on Sustainable Emerging Innovations in engineering and Technology, ICSEIET 2023

作者： Fatmawati, Maylia Novita, Mega Saputro, Nugroho Dwi Chauhan, Alok Singh Nada, Noora Qotrun Sinha, Amit Herlambang, Bambang Agus Gupta, Shruti Universitas Pgri Semarang Faculty of Engineering and Informatics Department of Informatics Semarang Indonesia Universitas Pgri Semarang Postgraduate Program of Science Education Semarang Indonesia School of Computing Science & Engineering Galgotias University Greater Noida India ABES Engineering College Department of Computer Science & Engineering Uttar Pradesh Ghaziabad201009 India

ISBN: (纸本)9798350329186

Maternal health is a critical concern, particularly for individuals who are pregnant and will shape the future generations. However, not all expectant mothers receive tailored attention and care for their unique health needs. Consequently, many mothers face high levels of health risks during pregnancy, highlighting the importance of classifying maternal health risks. Classification can help identify influential factors affecting maternal health and predict risk levels for individual mothers. In the field of data mining, various classification methods exist for analyzing complex datasets. This study focuses on two widely used algorithms: decision tree and k-Nearest Neighbor (kNN). By employing these algorithms, we aim to classify a dataset comprising 1,014 records of maternal health risk levels. Through cross-validation and T-tests, we rigorously evaluate the performance of the decision tree and kNN algorithms in this context. Our findings indicate that the kNN algorithm is more suitable for classifying maternal health risks, achieving a significantly higher accuracy of 71.50% compared to the decision tree algorithm's accuracy of 70.71%. This result establishes the superiority of the kNN algorithm in accurately classifying maternal health risks. These findings have implications for developing targeted interventions and tailored healthcare strategies to mitigate identified risks. © 2023 IEEE.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

The Implementation of Hybrid Semantic Ontology-based Model on Movie Recommendation System

The Implementation of Hybrid Semantic Ontology-based Model o...

引用

2022 International Conference on computer engineering, Network and Intelligent Multimedia, CENIM 2022

作者： Ifada, Noor Cahyaningrum, Evinda Widia Rachman, Fika Hastarita Department of Computer Engineering Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia

ISBN: (纸本)9781665476508

This paper adopts the Hybrid Semantic Ontology-based (HSO) model for a movie recommendation system. HSO consists of Collaborative Filtering (CF) and Content-based (CB) modules that respectively implement Matrix Factorization (MF) and ONTO Semantic Similarity algorithms. Since the feedback data type influences the MF algorithm choice, we individually implement the Non-Negative Matrix Factorization (NMF) and Singular Value Decomposition (SVD) algorithms for handling the movie rating data. Accordingly, our proposed methods are called HSO-NMF and HSO-SVD. Meanwhile, since the domain determines the ontology, we build and use a new movie ontology on the CB module. The experiments show that HSO performs the best when implemented using the SVD algorithm. On average, the increased percentages of HSO-SVD to HSO-NMF are 1.18% and 1.62% in Precision and NDCG metrics, respectively. The experiments also show that implementing the Hybrid model yields more accurate results than the CB or CF model. © 2022 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Five-Stage Pipelined 32-Bit RISC-V Base Integer Instruction Set Architecture Soft Microprocessor Core in VHDL 23

Five-Stage Pipelined 32-Bit RISC-V Base Integer Instruction ...

引用

23rd International Seminar on Intelligent Technology and Its Applications, ISITIA 2022

作者： Phangestu, Aaron Elson Mujiono, Ir. Totok Kom, M.I. Ahmad Zaini, St Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Computer Engineering Department Surabaya60111 Indonesia

ISBN: (数字)9781665460811

ISBN: (纸本)9781665460811

Proprietary technologies with complicated licensing currently dominate the microprocessor industry. As a result, we must seek out a freely available, open-source alternative. In this paper, we discussed the implementation of a five-stage pipelined soft processor core. The core uses the RISC-V RV32I Base Integer Instruction Set Architecture. RISC-V is an open standard ISA that is freely available to use and modify. To implement our processor core, we followed the FPGA design methodology. First, we implemented the design specification with the VHDL Hardware Description Language. Then, siwe mulated the design in the ModelSim simulation environment. Following the verification, we analyzed the resource usage, critical path, and maximum frequency of the processor, then uploaded the processor core to an actual Cyclone IV EP4CE6E22C FPGA. Our CPU core successfully executed all the RV32I instructions, except FENCE, ECALL, and CSR instructions. The proposed processor core runs on 2115 LUTs, 558 flip-flops, and 67,608 memory bits, with a maximum frequency of 62.95 MHz. © 2022 IEEE.

关键词： computer hardware description languages

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：